refactor: split monolithic phase tests into per-module test files
- rename test_admin_phase4.py -> test_admin.py, test_search.py -> test_searcher.py - split test_phase5.py into test_cleaner, test_embedder, test_image_extractor, test_pages - move schema tests from test_summarizer.py into dedicated test_schemas.py - add sample_papers_range and sample_papers_with_summary fixtures in conftest - update .gitignore to exclude all of data/
This commit is contained in:
+7
-239
@@ -1,15 +1,13 @@
|
||||
"""AI 总结服务测试 — Mock 全链路，不调用真实 pi。"""
|
||||
"""AI 总结服务测试 — summarize_one 状态流转、批量处理、DB 更新、文件操作。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
from datetime import date, datetime, timezone
|
||||
from pathlib import Path
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
from unittest.mock import AsyncMock, patch
|
||||
|
||||
import pytest
|
||||
from pydantic import ValidationError
|
||||
from sqlalchemy import text
|
||||
|
||||
from app.models import (
|
||||
@@ -20,193 +18,19 @@ from app.models import (
|
||||
SummaryStatus,
|
||||
TaskLock,
|
||||
)
|
||||
from app.services.schemas import (
|
||||
SummarySchema,
|
||||
assess_quality,
|
||||
classify_validation_error,
|
||||
flatten_for_db,
|
||||
from app.services.pdf_downloader import (
|
||||
PdfDownloadError,
|
||||
cleanup_tmp as _cleanup_tmp,
|
||||
)
|
||||
from app.services.pi_client import PiTimeoutError
|
||||
from app.services.schemas import SummarySchema
|
||||
from app.services.summarizer import (
|
||||
_classify_error,
|
||||
_save_files,
|
||||
_save_raw_output_only,
|
||||
_update_summary_in_db,
|
||||
summarize_batch,
|
||||
summarize_one,
|
||||
summarize_single,
|
||||
)
|
||||
from app.services.pi_client import (
|
||||
JsonNotFoundError,
|
||||
PiProcessError,
|
||||
PiTimeoutError,
|
||||
call_pi as _call_pi,
|
||||
extract_json as _extract_json,
|
||||
)
|
||||
from app.services.pdf_downloader import (
|
||||
PdfDownloadError,
|
||||
cleanup_tmp as _cleanup_tmp,
|
||||
)
|
||||
|
||||
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
# Schema 校验测试
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
|
||||
|
||||
class TestSummarySchema:
|
||||
"""Pydantic schema 校验。"""
|
||||
|
||||
def test_valid_summary(self, sample_summary_dict):
|
||||
schema = SummarySchema.model_validate(sample_summary_dict)
|
||||
assert schema.title_zh == "测试论文中文标题"
|
||||
assert len(schema.tags) == 3
|
||||
assert schema.motivation.problem
|
||||
|
||||
def test_missing_title_zh(self, sample_summary_dict):
|
||||
del sample_summary_dict["title_zh"]
|
||||
with pytest.raises(ValidationError) as exc_info:
|
||||
SummarySchema.model_validate(sample_summary_dict)
|
||||
assert classify_validation_error(exc_info.value) == "field_missing"
|
||||
|
||||
def test_empty_one_line(self, sample_summary_dict):
|
||||
sample_summary_dict["one_line"] = ""
|
||||
with pytest.raises(ValidationError):
|
||||
SummarySchema.model_validate(sample_summary_dict)
|
||||
|
||||
def test_empty_tags(self, sample_summary_dict):
|
||||
sample_summary_dict["tags"] = []
|
||||
with pytest.raises(ValidationError):
|
||||
SummarySchema.model_validate(sample_summary_dict)
|
||||
|
||||
def test_empty_motivation_problem(self, sample_summary_dict):
|
||||
sample_summary_dict["motivation"]["problem"] = ""
|
||||
with pytest.raises(ValidationError):
|
||||
SummarySchema.model_validate(sample_summary_dict)
|
||||
|
||||
def test_empty_method_key_idea(self, sample_summary_dict):
|
||||
sample_summary_dict["method"]["key_idea"] = ""
|
||||
with pytest.raises(ValidationError):
|
||||
SummarySchema.model_validate(sample_summary_dict)
|
||||
|
||||
def test_extra_fields_ignored(self, sample_summary_dict):
|
||||
sample_summary_dict["figures"] = ["fig1.png"]
|
||||
sample_summary_dict["takeaway"] = "important paper"
|
||||
schema = SummarySchema.model_validate(sample_summary_dict)
|
||||
assert not hasattr(schema, "figures")
|
||||
assert schema.title_zh # 正常解析
|
||||
|
||||
def test_flatten_for_db(self, sample_summary_dict):
|
||||
schema = SummarySchema.model_validate(sample_summary_dict)
|
||||
flat = flatten_for_db(schema)
|
||||
assert flat["one_line"] == schema.one_line
|
||||
assert flat["motivation_problem"] == schema.motivation.problem
|
||||
assert flat["method_key_idea"] == schema.method.key_idea
|
||||
assert "full_json" in flat
|
||||
assert "updated_at" in flat
|
||||
# JSON 字段可解析
|
||||
assert isinstance(json.loads(flat["prerequisites_json"]), dict)
|
||||
assert isinstance(json.loads(flat["method_steps_json"]), list)
|
||||
|
||||
|
||||
class TestQualityAssessment:
|
||||
"""质量分级测试。"""
|
||||
|
||||
def test_quality_normal(self, sample_summary_dict):
|
||||
schema = SummarySchema.model_validate(sample_summary_dict)
|
||||
assert assess_quality(schema) == "normal"
|
||||
|
||||
def test_quality_degraded_missing_goal(self, sample_summary_dict):
|
||||
sample_summary_dict["motivation"]["goal"] = ""
|
||||
sample_summary_dict["motivation"]["gap"] = ""
|
||||
sample_summary_dict["method"]["overview"] = ""
|
||||
sample_summary_dict["results"]["main_findings"] = []
|
||||
schema = SummarySchema.model_validate(sample_summary_dict)
|
||||
assert assess_quality(schema) == "degraded"
|
||||
|
||||
def test_quality_low_short_one_line(self, sample_summary_dict):
|
||||
sample_summary_dict["one_line"] = "短"
|
||||
schema = SummarySchema.model_validate(sample_summary_dict)
|
||||
assert assess_quality(schema) == "low"
|
||||
|
||||
def test_quality_low_short_key_idea(self, sample_summary_dict):
|
||||
sample_summary_dict["method"]["key_idea"] = "短"
|
||||
schema = SummarySchema.model_validate(sample_summary_dict)
|
||||
assert assess_quality(schema) == "low"
|
||||
|
||||
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
# JSON 提取测试
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
|
||||
|
||||
class TestJsonExtraction:
|
||||
"""pi 输出的 JSON 提取。"""
|
||||
|
||||
def test_direct_json(self, sample_summary_json):
|
||||
result = _extract_json(sample_summary_json)
|
||||
assert result["title_zh"] == "测试论文中文标题"
|
||||
|
||||
def test_fenced_code_block(self, sample_summary_json):
|
||||
raw = f"一些文字\n```json\n{sample_summary_json}\n```\n更多文字"
|
||||
result = _extract_json(raw)
|
||||
assert result["title_zh"] == "测试论文中文标题"
|
||||
|
||||
def test_fenced_without_lang(self, sample_summary_json):
|
||||
raw = f"文字\n```\n{sample_summary_json}\n```"
|
||||
result = _extract_json(raw)
|
||||
assert result["title_zh"] == "测试论文中文标题"
|
||||
|
||||
def test_embedded_braces(self, sample_summary_dict):
|
||||
json_str = json.dumps(sample_summary_dict, ensure_ascii=False)
|
||||
raw = f"Here is the summary:\n{json_str}\nEnd."
|
||||
result = _extract_json(raw)
|
||||
assert result["title_zh"] == "测试论文中文标题"
|
||||
|
||||
def test_no_json_raises(self):
|
||||
with pytest.raises(JsonNotFoundError):
|
||||
_extract_json("No JSON here at all.")
|
||||
|
||||
def test_json_without_title_zh_falls_through(self):
|
||||
"""不含 title_zh 的 JSON 不是我们要的。"""
|
||||
raw = json.dumps({"other": "data"})
|
||||
# 如果有其他合法 JSON 块也能返回，但没有就直接找最大块
|
||||
# 此场景 raw 本身就是一个 JSON dict，但没有 title_zh
|
||||
# 策略 1 会跳过（无 title_zh），策略 2 无代码块，策略 3 找到最大块
|
||||
result = _extract_json(raw)
|
||||
assert result == {"other": "data"} # 最大块兜底
|
||||
|
||||
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
# 错误分类测试
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
|
||||
|
||||
class TestErrorClassification:
|
||||
"""异常 → error_type 映射。"""
|
||||
|
||||
def test_pdf_download_error(self):
|
||||
assert _classify_error(PdfDownloadError("fail")) == "pdf_download_failed"
|
||||
|
||||
def test_timeout_error(self):
|
||||
assert _classify_error(PiTimeoutError("timeout")) == "timeout"
|
||||
|
||||
def test_process_error(self):
|
||||
assert _classify_error(PiProcessError(1, "stderr")) == "process_error"
|
||||
|
||||
def test_json_not_found(self):
|
||||
assert _classify_error(JsonNotFoundError("not found")) == "json_not_found"
|
||||
|
||||
def test_json_invalid(self):
|
||||
assert _classify_error(json.JSONDecodeError("bad", "", 0)) == "json_invalid"
|
||||
|
||||
def test_field_missing(self):
|
||||
try:
|
||||
SummarySchema.model_validate({"title_zh": ""}) # type: ignore
|
||||
except ValidationError as exc:
|
||||
assert _classify_error(exc) == "field_missing"
|
||||
|
||||
def test_unknown_error(self):
|
||||
assert _classify_error(RuntimeError("boom")) == "unknown"
|
||||
|
||||
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
@@ -675,59 +499,3 @@ class TestBatchSummarize:
|
||||
result = await summarize_batch(db_session)
|
||||
assert result["status"] == "success"
|
||||
assert result["total"] == 0
|
||||
|
||||
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
# Admin 路由鉴权测试
|
||||
# ═══════════════════════════════════════════════════════════════════════
|
||||
|
||||
|
||||
class TestAdminAuth:
|
||||
"""管理接口鉴权 — 只测 HTTP 层，mock 掉实际服务调用。"""
|
||||
|
||||
def test_no_token_returns_401(self, client):
|
||||
"""无 Bearer token 返回 401。"""
|
||||
resp = client.post("/admin/summarize")
|
||||
assert resp.status_code in (401, 403)
|
||||
|
||||
def test_wrong_token_returns_401(self, client):
|
||||
resp = client.post(
|
||||
"/admin/summarize",
|
||||
headers={"Authorization": "Bearer wrong-token"},
|
||||
)
|
||||
assert resp.status_code == 401
|
||||
|
||||
def test_correct_token_batch(self, client, admin_headers):
|
||||
"""正确 token 调用 batch summarize，mock 掉服务层。"""
|
||||
import app.config as config_mod
|
||||
|
||||
original = config_mod.settings.ADMIN_TOKEN
|
||||
config_mod.settings.ADMIN_TOKEN = "test-admin-token-12345"
|
||||
try:
|
||||
with patch("app.routes.admin.summarize_batch", new_callable=AsyncMock) as mock:
|
||||
mock.return_value = {"status": "success", "done": 0, "failed": 0, "total": 0}
|
||||
resp = client.post("/admin/summarize", headers=admin_headers)
|
||||
assert resp.status_code == 200
|
||||
assert resp.json()["status"] == "success"
|
||||
finally:
|
||||
config_mod.settings.ADMIN_TOKEN = original
|
||||
|
||||
def test_single_paper_not_found(self, client, admin_headers):
|
||||
"""单篇总结不存在的论文返回 404。"""
|
||||
import app.config as config_mod
|
||||
|
||||
original = config_mod.settings.ADMIN_TOKEN
|
||||
config_mod.settings.ADMIN_TOKEN = "test-admin-token-12345"
|
||||
try:
|
||||
with patch(
|
||||
"app.routes.admin.summarize_single",
|
||||
new_callable=AsyncMock,
|
||||
return_value={"status": "not_found", "arxiv_id": "nonexistent.99999"},
|
||||
):
|
||||
resp = client.post(
|
||||
"/admin/summarize/nonexistent.99999",
|
||||
headers=admin_headers,
|
||||
)
|
||||
assert resp.status_code == 404
|
||||
finally:
|
||||
config_mod.settings.ADMIN_TOKEN = original
|
||||
|
||||
Reference in New Issue
Block a user